Abstract: To address issues such as high equipment costs, reliance on camera calibration, and poor adaptability to complex shapes in traditional bulk grain pile volume measurement methods, this study proposes an intelligent estimation method for bulk grain pile volume based on DUSt3R 3D reconstruction point clouds. This method leverages DUSt3R's attention mechanism and dense matching technology to generate 3D point clouds end-to-end without requiring pre-calibrated camera parameters. A point cloud optimization module tailored to grain pile characteristics is constructed. Combining statistical filtering with RANSAC plane detection technology enhances point cloud noise removal capabilities. DBSCAN clustering achieves precise segmentation between the grain pile and the ground surface. This approach effectively eliminates dependence on camera calibration, significantly improves point cloud noise processing and segmentation accuracy, and adaptively fits complex grain pile morphologies through dynamic grid projection and Alpha Shape surface reconstruction. It ensures measurement accuracy while substantially reducing hardware costs, demonstrating excellent engineering applicability. Validation tests on six typical grain pile morphologies yielded an average measurement error of approximately 5%, achievable using only standard cameras for data acquisition. This volume measurement method can be efficiently integrated with the flat grain robot operation equipment, providing a low-cost, high-precision technical solution for bulk grain pile volume measurement and automated operation guidance.